Merge pull request #252 from itsDNNS/feat/196-traceroute-burst-capture

feat(cm): traceroute burst capture (#196)

Author: itsDNNS

Dockerfile

@@ -11,8 +11,10 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 COPY requirements.txt .
 RUN pip install --no-cache-dir --prefix=/install -r requirements.txt
 COPY tools/icmp_probe_helper.c /build/icmp_probe_helper.c
+COPY tools/traceroute_helper.c /build/traceroute_helper.c
 RUN mkdir -p /build/out && \
-    gcc -O2 -Wall -o /build/out/docsight-icmp-helper /build/icmp_probe_helper.c
+    gcc -O2 -Wall -o /build/out/docsight-icmp-helper /build/icmp_probe_helper.c && \
+    gcc -O2 -Wall -o /build/out/docsight-traceroute-helper /build/traceroute_helper.c
 
 # --- runtime stage: slim final image ---
 FROM python:3.12-slim
@@ -22,13 +24,16 @@ RUN echo "${VERSION}" > /app/VERSION
 
 COPY --from=builder /install /usr/local
 COPY --from=builder /build/out/docsight-icmp-helper /usr/local/bin/docsight-icmp-helper
+COPY --from=builder /build/out/docsight-traceroute-helper /usr/local/bin/docsight-traceroute-helper
 
 # Keep elevated privileges scoped to the dedicated ICMP helper.
 RUN apt-get update && apt-get install -y --no-install-recommends \
     gosu \
     libjpeg62-turbo \
     && chown root:root /usr/local/bin/docsight-icmp-helper \
     && chmod 4755 /usr/local/bin/docsight-icmp-helper \
+    && chown root:root /usr/local/bin/docsight-traceroute-helper \
+    && chmod 4755 /usr/local/bin/docsight-traceroute-helper \
     && rm -rf /var/lib/apt/lists/*
 
 RUN adduser --disabled-password --gecos "" --uid 1000 appuser && \

app/blueprints/config_bp.py

@@ -116,6 +116,13 @@ def api_demo_migrate():
         return jsonify({"success": False, "error": "Storage not initialized"}), 500
     try:
         purged = _storage.purge_demo_data()
+        # Purge demo traceroute traces from Connection Monitor
+        import os
+        from app.modules.connection_monitor.storage import ConnectionMonitorStorage
+        cm_db_path = os.path.join(os.environ.get("DATA_DIR", "/data"), "connection_monitor.db")
+        if os.path.exists(cm_db_path):
+            cm_storage = ConnectionMonitorStorage(cm_db_path)
+            cm_storage.purge_demo_traces()
         _config_manager.save({"demo_mode": False})
         _storage.max_days = _config_manager.get("history_days", 7)
         audit_log.info("Demo migration: ip=%s purged=%d rows", _get_client_ip(), purged)

app/collectors/demo.py

@@ -993,6 +993,94 @@ def _seed_connection_monitor_data(self, now):
 
         log.info("Demo: seeded %d connection monitor samples (%d days, 3 targets)", len(rows), days)
 
+        # --- Seed traceroute traces ---
+        self._seed_traceroute_traces(cm, cf_id, gg_id, now, rng)
+
+    def _seed_traceroute_traces(self, cm, cf_id, gg_id, now, rng):
+        """Seed realistic traceroute traces for demo targets."""
+        import hashlib
+
+        # Realistic hop templates: home -> ISP -> backbone -> target
+        hop_templates = {
+            cf_id: [
+                {"hop_ip": "192.168.178.1", "hop_host": "fritz.box", "base_lat": 1.2},
+                {"hop_ip": "62.155.243.1", "hop_host": "dslam-ffm.telekom.de", "base_lat": 5.8},
+                {"hop_ip": "62.157.250.22", "hop_host": "cr-ffm01.telekom.de", "base_lat": 8.1},
+                {"hop_ip": "62.157.250.89", "hop_host": "cr-ffm02.telekom.de", "base_lat": 8.9},
+                {"hop_ip": "80.156.160.178", "hop_host": "decix-peer.telekom.de", "base_lat": 10.3},
+                {"hop_ip": "172.71.128.2", "hop_host": "cloudflare-ic.decix.net", "base_lat": 11.0},
+                {"hop_ip": "172.71.128.34", "hop_host": None, "base_lat": 11.5},
+                {"hop_ip": "104.16.132.229", "hop_host": "one.one.one.one", "base_lat": 11.8},
+                {"hop_ip": None, "hop_host": None, "base_lat": None},  # timeout hop
+                {"hop_ip": "172.71.0.150", "hop_host": None, "base_lat": 12.1},
+                {"hop_ip": "1.1.1.1", "hop_host": "one.one.one.one", "base_lat": 12.4},
+            ],
+            gg_id: [
+                {"hop_ip": "192.168.178.1", "hop_host": "fritz.box", "base_lat": 1.1},
+                {"hop_ip": "62.155.243.1", "hop_host": "dslam-ffm.telekom.de", "base_lat": 5.6},
+                {"hop_ip": "62.157.250.22", "hop_host": "cr-ffm01.telekom.de", "base_lat": 8.0},
+                {"hop_ip": "62.157.250.89", "hop_host": "cr-ffm02.telekom.de", "base_lat": 8.7},
+                {"hop_ip": "80.156.160.178", "hop_host": "decix-peer.telekom.de", "base_lat": 10.1},
+                {"hop_ip": "209.85.149.32", "hop_host": "google-ic.decix.net", "base_lat": 11.2},
+                {"hop_ip": "108.170.236.57", "hop_host": None, "base_lat": 12.0},
+                {"hop_ip": "142.251.51.15", "hop_host": None, "base_lat": 13.1},
+                {"hop_ip": None, "hop_host": None, "base_lat": None},  # timeout hop
+                {"hop_ip": "108.170.232.97", "hop_host": None, "base_lat": 13.8},
+                {"hop_ip": "142.250.236.131", "hop_host": None, "base_lat": 14.2},
+                {"hop_ip": "8.8.8.8", "hop_host": "dns.google", "base_lat": 14.5},
+            ],
+        }
+
+        trace_configs = [
+            {"target_id": cf_id, "days_ago": 5, "trigger": "outage", "reached": True},
+            {"target_id": cf_id, "days_ago": 2, "trigger": "packet_loss", "reached": True},
+            {"target_id": cf_id, "days_ago": 0, "trigger": "manual", "reached": True},
+            {"target_id": gg_id, "days_ago": 4, "trigger": "outage", "reached": True},
+            {"target_id": gg_id, "days_ago": 1, "trigger": "manual", "reached": True},
+        ]
+
+        for tc in trace_configs:
+            template = hop_templates[tc["target_id"]]
+            hops = []
+            ips_for_fp = []
+            for i, tmpl in enumerate(template):
+                if tmpl["base_lat"] is None:
+                    # Timeout hop
+                    hops.append({
+                        "hop_index": i + 1,
+                        "hop_ip": None,
+                        "hop_host": None,
+                        "latency_ms": None,
+                        "probes_responded": 0,
+                    })
+                    ips_for_fp.append("*")
+                else:
+                    lat = round(tmpl["base_lat"] + rng.uniform(-0.5, 0.5), 2)
+                    probes = 3 if rng.random() > 0.05 else rng.randint(1, 2)
+                    hops.append({
+                        "hop_index": i + 1,
+                        "hop_ip": tmpl["hop_ip"],
+                        "hop_host": tmpl["hop_host"],
+                        "latency_ms": lat,
+                        "probes_responded": probes,
+                    })
+                    ips_for_fp.append(tmpl["hop_ip"] or "*")
+
+            fp = hashlib.md5(">".join(ips_for_fp).encode()).hexdigest()[:16]
+            ts = (now - timedelta(days=tc["days_ago"], hours=rng.randint(0, 12))).timestamp()
+
+            cm.save_trace(
+                target_id=tc["target_id"],
+                timestamp=ts,
+                trigger_reason=tc["trigger"],
+                hops=hops,
+                route_fingerprint=fp,
+                reached_target=tc["reached"],
+                is_demo=True,
+            )
+
+        log.info("Demo: seeded %d traceroute traces", len(trace_configs))
+
     @staticmethod
     def _generate_bqm_png(width=800, height=200, seed=0):
         """Generate a simple BQM-style quality graph as PNG bytes."""

app/main.py

@@ -294,6 +294,12 @@ def _run_collector(collector):
             stop_event.wait(1)
     finally:
         executor.shutdown(wait=False, cancel_futures=True)
+        for c in collectors:
+            if hasattr(c, "stop"):
+                try:
+                    c.stop()
+                except Exception:
+                    pass
 
     # Cleanup MQTT
     if mqtt_pub:

app/modules/connection_monitor/collector.py

@@ -9,6 +9,8 @@
 from app.modules.connection_monitor.event_rules import ConnectionEventRules
 from app.modules.connection_monitor.probe import ProbeEngine
 from app.modules.connection_monitor.storage import ConnectionMonitorStorage
+from app.modules.connection_monitor.traceroute_probe import TracerouteProbe
+from app.modules.connection_monitor.traceroute_trigger import TracerouteTrigger
 
 logger = logging.getLogger(__name__)
 
@@ -29,6 +31,7 @@ def __init__(self, config_mgr, storage, web, **kwargs):
 
         method = config_mgr.get("connection_monitor_probe_method", "auto")
         self._probe = ProbeEngine(method=method)
+        self._traceroute_probe = TracerouteProbe()
         self._last_probe: dict[int, float] = {}
         self._last_cleanup = 0.0
         self._event_rules = ConnectionEventRules(
@@ -39,6 +42,10 @@ def __init__(self, config_mgr, storage, web, **kwargs):
         data_dir = os.environ.get("DATA_DIR", "/data")
         db_path = os.path.join(data_dir, "connection_monitor.db")
         self._cm_storage = ConnectionMonitorStorage(db_path)
+        self._traceroute_trigger = TracerouteTrigger(
+            probe=self._traceroute_probe,
+            storage=self._cm_storage,
+        )
 
         self._seeded = False
         self._smart_capture = None
@@ -92,6 +99,7 @@ def collect(self) -> CollectorResult:
                     self._config_mgr.get("connection_monitor_retention_days", 0)
                 )
                 self._cm_storage.cleanup(retention)
+                self._cm_storage.cleanup_traces(retention)
                 self._last_cleanup = now
 
             return CollectorResult.ok(self.name, {"probed": len(due)})
@@ -153,6 +161,9 @@ def _check_events(self, samples: list[dict]):
             )
             all_events.extend(events)
 
+        for event in all_events:
+            self._traceroute_trigger.on_event(event)
+
         if all_events and hasattr(self._core_storage, "save_events_with_ids"):
             self._core_storage.save_events_with_ids(all_events)
             if self._smart_capture:
@@ -175,3 +186,7 @@ def get_storage(self) -> ConnectionMonitorStorage:
     def get_probe(self) -> ProbeEngine:
         """Expose probe engine for capability endpoint."""
         return self._probe
+
+    def stop(self):
+        """Shutdown background resources."""
+        self._traceroute_trigger.shutdown()

app/modules/connection_monitor/i18n/de.json

@@ -54,5 +54,19 @@
   "cm_resolution_raw": "Rohdaten",
   "cm_resolution_1min": "1-Min-Durchschnitte",
   "cm_resolution_5min": "5-Min-Durchschnitte",
-  "cm_resolution_1hr": "1-Std-Durchschnitte"
+  "cm_resolution_1hr": "1-Std-Durchschnitte",
+  "traceroute.run_button": "Traceroute starten",
+  "traceroute.running": "Traceroute wird ausgeführt...",
+  "traceroute.result": "Traceroute-Ergebnis",
+  "traceroute.trigger_manual": "Manuell",
+  "traceroute.trigger_outage": "Ausfall",
+  "traceroute.trigger_packet_loss": "Paketverlust",
+  "traceroute.hop": "Hop",
+  "traceroute.hops": "Hops",
+  "traceroute.reached": "Ziel erreicht",
+  "traceroute.not_reached": "Ziel nicht erreicht",
+  "traceroute.history": "Traceroute-Verlauf",
+  "traceroute.no_traces": "Noch keine Traceroutes aufgezeichnet.",
+  "traceroute.probes_responded": "Antworten",
+  "traceroute.partial_result": "Teilergebnis (Zeitüberschreitung)"
 }

app/modules/connection_monitor/i18n/en.json

@@ -54,5 +54,19 @@
   "cm_resolution_raw": "Raw samples",
   "cm_resolution_1min": "1-min averages",
   "cm_resolution_5min": "5-min averages",
-  "cm_resolution_1hr": "1-hour averages"
+  "cm_resolution_1hr": "1-hour averages",
+  "traceroute.run_button": "Run Traceroute",
+  "traceroute.running": "Running traceroute...",
+  "traceroute.result": "Traceroute Result",
+  "traceroute.trigger_manual": "Manual",
+  "traceroute.trigger_outage": "Outage",
+  "traceroute.trigger_packet_loss": "Packet Loss",
+  "traceroute.hop": "Hop",
+  "traceroute.hops": "Hops",
+  "traceroute.reached": "Target reached",
+  "traceroute.not_reached": "Target not reached",
+  "traceroute.history": "Traceroute History",
+  "traceroute.no_traces": "No traceroutes recorded yet.",
+  "traceroute.probes_responded": "Probes",
+  "traceroute.partial_result": "Partial result (timeout)"
 }

app/modules/connection_monitor/i18n/es.json

@@ -54,5 +54,19 @@
   "cm_resolution_raw": "Datos crudos",
   "cm_resolution_1min": "Promedios de 1 min",
   "cm_resolution_5min": "Promedios de 5 min",
-  "cm_resolution_1hr": "Promedios de 1 h"
+  "cm_resolution_1hr": "Promedios de 1 h",
+  "traceroute.run_button": "Ejecutar Traceroute",
+  "traceroute.running": "Ejecutando traceroute...",
+  "traceroute.result": "Resultado del Traceroute",
+  "traceroute.trigger_manual": "Manual",
+  "traceroute.trigger_outage": "Corte",
+  "traceroute.trigger_packet_loss": "Perdida de paquetes",
+  "traceroute.hop": "Salto",
+  "traceroute.hops": "Saltos",
+  "traceroute.reached": "Objetivo alcanzado",
+  "traceroute.not_reached": "Objetivo no alcanzado",
+  "traceroute.history": "Historial de Traceroute",
+  "traceroute.no_traces": "Aun no se han registrado traceroutes.",
+  "traceroute.probes_responded": "Sondas",
+  "traceroute.partial_result": "Resultado parcial (timeout)"
 }

app/modules/connection_monitor/i18n/fr.json

@@ -54,5 +54,19 @@
   "cm_resolution_raw": "Donnees brutes",
   "cm_resolution_1min": "Moyennes 1 min",
   "cm_resolution_5min": "Moyennes 5 min",
-  "cm_resolution_1hr": "Moyennes 1 h"
+  "cm_resolution_1hr": "Moyennes 1 h",
+  "traceroute.run_button": "Lancer Traceroute",
+  "traceroute.running": "Traceroute en cours...",
+  "traceroute.result": "Resultat du Traceroute",
+  "traceroute.trigger_manual": "Manuel",
+  "traceroute.trigger_outage": "Panne",
+  "traceroute.trigger_packet_loss": "Perte de paquets",
+  "traceroute.hop": "Saut",
+  "traceroute.hops": "Sauts",
+  "traceroute.reached": "Cible atteinte",
+  "traceroute.not_reached": "Cible non atteinte",
+  "traceroute.history": "Historique Traceroute",
+  "traceroute.no_traces": "Aucun traceroute enregistre.",
+  "traceroute.probes_responded": "Sondes",
+  "traceroute.partial_result": "Resultat partiel (timeout)"
 }

app/modules/connection_monitor/routes.py

@@ -6,7 +6,7 @@
 import math
 import re
 import time
-from datetime import datetime
+from datetime import datetime, timezone
 
 from flask import Blueprint, jsonify, request, Response
 
@@ -50,6 +50,31 @@ def _get_probe_engine():
     return ProbeEngine(method=method)
 
 
+_traceroute_probe = None
+
+
+def _get_traceroute_probe():
+    global _traceroute_probe
+    if _traceroute_probe is None:
+        from app.modules.connection_monitor.traceroute_probe import TracerouteProbe
+        _traceroute_probe = TracerouteProbe()
+    return _traceroute_probe
+
+
+def _epoch_to_iso(ts):
+    return datetime.fromtimestamp(ts, tz=timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
+
+
+def _hop_to_dict(hop):
+    return {
+        "hop_index": hop.hop_index,
+        "hop_ip": hop.hop_ip,
+        "hop_host": hop.hop_host,
+        "latency_ms": hop.latency_ms,
+        "probes_responded": hop.probes_responded,
+    }
+
+
 # --- Targets ---
 
 @bp.route("/api/connection-monitor/targets", methods=["GET"])
@@ -516,3 +541,67 @@ def api_export_csv(target_id):
 def api_capability():
     probe = _get_probe_engine()
     return jsonify(probe.capability_info())
+
+
+# --- Traceroute ---
+
+@bp.route("/api/connection-monitor/traceroute/<int:target_id>", methods=["POST"])
+@require_auth
+def api_run_traceroute(target_id):
+    storage = _get_cm_storage()
+    target = storage.get_target(target_id)
+    if not target:
+        return jsonify({"error": "Target not found"}), 404
+
+    probe = _get_traceroute_probe()
+    result = probe.run(target["host"])
+
+    trace_id = storage.save_trace(
+        target_id=target_id,
+        timestamp=time.time(),
+        trigger_reason="manual",
+        hops=[{
+            "hop_index": h.hop_index, "hop_ip": h.hop_ip,
+            "hop_host": h.hop_host, "latency_ms": h.latency_ms,
+            "probes_responded": h.probes_responded,
+        } for h in result.hops],
+        route_fingerprint=result.route_fingerprint,
+        reached_target=result.reached_target,
+    )
+
+    return jsonify({
+        "trace_id": trace_id,
+        "timestamp": _epoch_to_iso(time.time()),
+        "trigger_reason": "manual",
+        "reached_target": result.reached_target,
+        "hop_count": len(result.hops),
+        "route_fingerprint": result.route_fingerprint,
+        "hops": [_hop_to_dict(h) for h in result.hops],
+    })
+
+
+@bp.route("/api/connection-monitor/traces/<int:target_id>")
+@require_auth
+def api_get_traces(target_id):
+    storage = _get_cm_storage()
+    start = request.args.get("start", type=float)
+    end = request.args.get("end", type=float)
+    limit = request.args.get("limit", 100, type=int)
+    limit = max(1, min(limit, 1000))
+    traces = storage.get_traces(target_id, start=start, end=end, limit=limit)
+    for t in traces:
+        t["timestamp"] = _epoch_to_iso(t["timestamp"])
+    return jsonify(traces)
+
+
+@bp.route("/api/connection-monitor/trace/<int:trace_id>")
+@require_auth
+def api_get_trace_detail(trace_id):
+    storage = _get_cm_storage()
+    trace = storage.get_trace(trace_id)
+    if not trace:
+        return jsonify({"error": "Trace not found"}), 404
+    hops = storage.get_trace_hops(trace_id)
+    trace["timestamp"] = _epoch_to_iso(trace["timestamp"])
+    trace["hops"] = hops
+    return jsonify(trace)